Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12936
    Prev
    Next
    INDEX
    Explanations

    instructions related to a task or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carav
    -0.41
     وز
    -0.40
    如今
    -0.40
    EMBLE
    -0.39
     איז
    -0.38
     Portanto
    -0.38
     hiệu
    -0.38
    哪
    -0.38
     tert
    -0.38
    *
    -0.37
    POSITIVE LOGITS
    FilterChain
    0.79
    principalColumn
    0.79
     >=",
    0.73
     GenerationType
    0.69
    ]")]
    0.68
     <=",
    0.67
     IBOutlet
    0.63
    êques
    0.63
    MigrationBuilder
    0.62
     Jérusalem
    0.62
    Activations Density 0.279%

    No Known Activations